Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2741ba0c1658b431f78e8aba253ff71d0a305a5cae30354726e68abd8e6b1dd4
+oid sha256:564000152e04f34ad9cff380fb4b4d07e96b2901edc2e7c66cb072a2ec50b829
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62b9c91f473c7a39b55a48655c9b58d247ecaad6471a350c4b2f59791c6bea78
+oid sha256:5ca718b881699e51c73349b0ef9642ba4daf6b2d09966e7ce7f852ac6cf4ef61
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8c9268a88f9a768a56781b2f922982dd8b112b100e2229d10de13e4538eb16e
+oid sha256:9c0ff0504c317a650346ee57e6218cab84ea2865e8a3e9847fe8a9d7e5cc0868
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0b2196e2f29a6683acf49e9b6eb98e7393791df29402c783d469811f16cf26
+oid sha256:09921ec2b52ed1c6b0f6ed69eeab044aae49b679e52ca9804dd8ad029e7ac795
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8804633617401123,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 1.8469738960266113,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.5100182149362478,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,13 +91,27 @@
       "eval_samples_per_second": 43.709,
       "eval_steps_per_second": 5.469,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 1.8572,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 1.8469738960266113,
+      "eval_runtime": 143.4729,
+      "eval_samples_per_second": 43.73,
+      "eval_steps_per_second": 5.471,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.576193971702989e+16,
+  "total_flos": 4.169402919360922e+16,
   "trial_name": null,
   "trial_params": null
 }